Back to models
Minimax M2.7
OpenRouter
205K context$0.28/M input$1.20/M output
1581
Avg Score
76.4
Avg Cost
$0.05
Score/$
1403.5
Runs
70
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languageexpert
2538refactoringexpert
2440multi-languagehard
2087multi-language
1817backendeasy
1794backendexpert
1773refactoring
1753from-scratchhard
1749from-scratcheasy
1733refactoringmedium
1719frontendexpert
1689backendhard
1665code-reviewhard
1637debuggingmedium
1632backend
1615debuggingexpert
1602debugginghard
1573from-scratch
1572debugging
1560code-review
1517frontendmedium
1514full-stackhard
1513code-reviewmedium
1509full-stack
1506backendmedium
1504full-stackmedium
1484frontend
1475frontendeasy
1449backendmaster
1447frontendmaster
1418from-scratchmedium
1393frontendhard
1046from-scratchexpert
985All Results
| Task | Category | Score |
|---|---|---|
| Build 3D browser game with physics and multiplayer sync | frontend | 58.8 |
| Migrate Express monolith to modular architecture | backend | 66.4 |
| Add streaming SSE endpoint for LLM chat | backend | 54.4 |
| Build production website with auth and members area | frontend | 69.0 |
| Add file upload with S3 presigned URLs | backend | 74.3 |
| Build SaaS admin dashboard from scratch | from-scratch | 69.2 |
| Add Redis caching layer to Express API | backend | 78.8 |
| Fix memory leak in event handler | debugging | 56.5 |
| Convert React app to PWA with offline support | frontend | 73.4 |
| Build terminal UI dashboard | from-scratch | 61.8 |
| Port Python CLI to Rust | multi-language | 75.5 |
| Add GraphQL layer over REST API | multi-language | 83.3 |
| Refactor monolithic handler to CQRS | refactoring | 82.0 |
| Add WebSocket real-time updates | full-stack | 70.8 |
| Build real-time portfolio risk calculator | backend | 76.5 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 87.2 |
| Build interactive data visualization dashboard | frontend | 68.2 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 78.0 |
| Fix N+1 query in dashboard | backend | 69.8 |
| Build CLI tool with subcommands and config | from-scratch | 75.4 |
| Replace console.log with structured logging | refactoring | 77.9 |
| Zero-downtime schema migration | full-stack | 82.8 |
| Debug race condition in worker pool | debugging | 89.7 |
| Add rate limiting middleware | backend | 77.5 |
| Fix deadlocking transaction patterns in Flask app | backend | 86.0 |
| Build REST API from scratch | from-scratch | 81.6 |
| Optimize bloated React bundle under 500KB | frontend | 69.8 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 89.2 |
| Build LLM evaluation harness with structured grading | backend | 81.5 |
| Add i18n with locale routing to Next.js app | full-stack | 75.3 |
| Code review: identify security vulns | code-review | 73.3 |
| Migrate callback-hell Express app to async/await | refactoring | 86.8 |
| Build materialized view refresh pipeline for analytics | backend | 74.0 |
| Add cursor-based pagination to REST API | backend | 79.2 |
| Write tests for untested legacy Flask service | code-review | 82.7 |
| Implement background job scheduler with persistence | backend | 78.8 |
| Implement JWT auth middleware | backend | 63.9 |
| Fix and extend Chrome browser extension | frontend | 63.6 |
| Add retry logic and dead letter queue to Python task queue | backend | 78.5 |
| Optimize slow Postgres queries in Flask app | backend | 82.8 |
| Fix auth bypass vulnerability | debugging | 93.4 |
| Split 1100-line god file into proper modules | refactoring | 80.5 |
| Build multi-tool LLM agent runtime | backend | 80.4 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 89.4 |
| Build distributed node cluster with gossip protocol | from-scratch | 67.5 |
| Remove AI slop and over-engineering from codebase | refactoring | 81.4 |
| Implement transformer inference engine with KV cache | from-scratch | 66.7 |
| Fix race conditions in order matching engine | backend | 90.9 |
| Build MCP server for database management | backend | 80.7 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 85.6 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 70.6 |
| Build codebase indexer for LLM context windows | from-scratch | 70.3 |
| Implement zero-trust API authentication layer | backend | 71.7 |
| Fix React hydration mismatch | frontend | 74.4 |
| Write integration tests for payment flow | code-review | 74.8 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 72.2 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 84.5 |
| Add slash commands and moderation to Discord bot | backend | 73.3 |
| Add Google OAuth2 login to Express app | full-stack | 65.4 |
| Debug and fix 6 broken database triggers and constraints | debugging | 80.0 |
| Write complex SQL report with window functions | backend | 73.3 |
| Fix flaky test suite | debugging | 80.0 |
| Implement multi-tenant row-level security in Postgres | backend | 81.0 |
| Fix broken responsive layout | frontend | 71.8 |
| Build RAG pipeline with vector search | backend | 83.8 |
| Fix hallucination and context window bugs in RAG agent | backend | 79.8 |
| Implement Stripe webhook handler | backend | 81.7 |
| Dockerize Node.js monorepo | full-stack | 73.3 |
| Fix broken GitHub Actions CI pipeline | debugging | 91.5 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 74.0 |